Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming syntax that includes special characters, colons, and parameter assignments

    oai_token-act-pair · gemini-2.0-flash

    colon and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NewLabel
    -0.43
     senior
    -0.42
    日语
    -0.41
     vernac
    -0.38
    PTI
    -0.38
    apt
    -0.38
    senior
    -0.38
     nhat
    -0.37
    териалы
    -0.37
    commons
    -0.37
    POSITIVE LOGITS
    parsedMessage
    0.90
    saraba
    0.78
    DeleteBehavior
    0.77
    0.77
     EconPapers
    0.77
    AutoField
    0.75
    principalColumn
    0.75
    ftagPool
    0.73
     ویکی‌پدی
    0.73
    addCriterion
    0.73
    Act Density 2.328%

    No Known Activations